Security: Security Experts Paired with Self-Learning AI Algorithms Battle Cyber Crimes

Home › Security › Security: Security Experts Paired with Self-Learning AI Algorithms Battle Cyber Crimes By Dick Weisinger MIT AI Laboratory (CSAIL) scientists are using machine learning to help stop cybercrimes.  The MIT algorithm called AI2 (AI squared) reportedly is three times more effective in spotting cyber activities than other methods.  The algorithm boasts of being able to detect 85 percent of cyber crimes. Kalyan Veeramachaneni, a research scientist at MIT’s CSAIL, said that “You can think about the system as a virtual analyst.  It continuously generates new models that it can refine in as little as a few hours, meaning it can improve its detection rates significantly and rapidly. The more attacks the system detects, the more analyst feedback it receives, which, in turn, improves the accuracy of future predictions.  That…


Link to Full Article: Security: Security Experts Paired with Self-Learning AI Algorithms Battle Cyber Crimes